Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning.
Rodrigo Toro IcarteToryn Q. KlassenRichard Anthony ValenzanoSheila A. McIlraithPublished in: J. Artif. Intell. Res. (2022)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- inverse reinforcement learning
- state space
- optimal policy
- partially observable
- markov decision process
- hierarchical reinforcement learning
- policy search
- function approximation
- multiple agents
- average reward
- model free
- initially unknown
- learning agent
- machine learning
- total reward
- control policies
- state action
- transition probabilities
- dynamic systems
- generative model
- bayesian networks
- learning algorithm